Due to the significance of transportation planning, traffic management, and dispatch optimization, predicting passenger origin–destination has emerged as a crucial requirement for intelligent transportation systems management. In this study, we present a model designed to forecast the origin and destination of travels within a specified time window. To derive meaningful travel flows, we employ K-means clustering in a four-dimensional space with a maximum cluster size constraint for origin and destination zones. Given the large number of clusters, we utilize non-negative matrix factorization to reduce the number of travel clusters. Furthermore, we implement a stacked recurrent neural network model to predict the travel count in each cluster. A comparison of our results with existing models reveals that our proposed model achieves a 5–7% lower mean absolute percentage error (MAPE) for 1-h time windows and a 14% lower MAPE for 30-min time windows.
Proposing a model for predicting passenger origin–destination in online taxi-hailing systems
Predicting passenger origin–destination P. Golshanrad et al.
Public Transp
Public Transport ; 17 , 1 ; 121-151
2025-03-01
31 pages
Article (Journal)
Electronic Resource
English
Passenger origin–destination prediction , Origin–destination flow prediction , Recurrent neural networks , Online taxi-hailing Information and Computing Sciences , Artificial Intelligence and Image Processing , Business and Management , Operations Research/Decision Theory , Automotive Engineering , Computer-Aided Engineering (CAD, CAE) and Design , Transportation
Proposing a model for predicting passenger origin–destination in online taxi-hailing systems
Springer Verlag | 2025
|Safety protection system for passenger and driver in online taxi-hailing service and taxi
European Patent Office | 2020
|Review of shared online hailing and autonomous taxi services
Taylor & Francis Verlag | 2023
|